Increased computing power and the Web have made
information widely accessible.  In turn, this has encouraged the
development of recommendation systems that help users find items of
interest, such as books or restaurants.  Such systems are more useful
when they personalize themselves to each user's preferences,
thus making the recommendation process more efficient and effective. 
In this paper, we present a new approach to recommendation systems:
that of personalized conversational recommendation.  This system uses
the complementary strengths of recommendation systems and dialogue
systems to overcome their respective deficiencies.
We present a system -- the Adaptive Place Advisor -- implementing our
ideas.  This system  treats item selection as an 
interactive, conversational process, with the program inquiring about 
item attributes and the user responding.  The system incorporates a 
user model that contains item, attribute, and value preferences, 
which it updates during each conversation and maintains across sessions.  
The Place Advisor utilizes both the conversational context and the user 
model to retrieve candidate items from a database. It uses personalized 
heuristics to select which attribute to ask about in order to narrow 
down and rank possible choices.
We report experimental results demonstrating the effectiveness 
of user modeling in reducing the time and number of interactions 
required to find a satisfactory item.